Optimization of directed acyclic graph (DAG) structures has many applications, such as neural architecture search (NAS) and probabilistic graphical model learning. Encoding DAGs into real vectors is a dominant component in most neural-network-based DAG optimization frameworks. Currently, most DAG encoders use an asynchronous message passing scheme which sequentially processes nodes according to the dependency between nodes in a DAG. That is, a node must not be processed until all its predecessors are processed. As a result, they are inherently not parallelizable. In this work, we propose a Parallelizable Attention-based Computation structure Encoder (PACE) that processes nodes simultaneously and encodes DAGs in parallel. We demonstrate the superiority of PACE through encoder-dependent optimization subroutines that search the optimal DAG structure based on the learned DAG embeddings. Experiments show that PACE not only improves the effectiveness over previous sequential DAG encoders with a significantly boosted training and inference speed, but also generates smooth latent (DAG encoding) spaces that are beneficial to downstream optimization subroutines. Our source code is available at \url{https://github.com/zehao-dong/PACE}
翻译:定向环形图(DAG) 优化定向环形图(DAG) 结构的优化有许多应用, 如神经结构搜索(NAS) 和概率图形模型学习。 将 DAG 编码成真实矢量是大多数以神经- 网络为基础的 DAG 优化框架中的主导组成部分。 目前, 大多数 DAG 编码器使用一个非同步信息传递方案, 该程序根据在 DAG 中各节点之间的依赖性依次顺序处理 DAG 。 也就是说, 一个节点不能被处理, 直到所有前身都处理完毕。 结果, 它们本质上是不可平行的。 在这项工作中, 我们提议一个平行的基于注意的配置和编码 DAG 优化框架( PAC ) 。 我们通过基于已学的 DAG 嵌入式搜索最佳 DAG 结构来显示 PACE 的优越性 。 实验显示 PACE 不仅提高了以往连续的 DAG 编码器的效能, 并且大大提升了培训和推导速度 。 我们的DAGAGDODO /DODODODODOLODOLO 的代码源是有利的。